Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
FinMMDocR: Benchmarking Financial Multimodal Reasoning with Scenario Awareness, Document Understanding, and Multi-Step Computation
Zichen Tang, Haihong E, Rongjin Li +18
We introduce FinMMDocR, a novel bilingual multimodal benchmark for evaluating multimodal large language models (MLLMs) on real-world financial numerical reasoning. Compared to exis…
cs.CV2025
Image Tokens Matter: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing
Weixing Wang, Zifeng Ding, Jindong Gu +4
Large Vision-Language Models (LVLMs) with discrete image tokenizers unify multimodal representations by encoding visual inputs into a finite set of tokens. Despite their effectiven…
cs.CV2024
Decompose and Leverage Preferences from Expert Models for Improving Trustworthiness of MLLMs
Rui Cao, Yuming Jiang, Michael Schlichtkrull +1
Multimodal Large Language Models (MLLMs) can enhance trustworthiness by aligning with human preferences. As human preference labeling is laborious, recent works employ evaluation m…